improve

improve is a skill for Claude Code from Tyler-R-Kendrick/agent-skills. It costs 215 tokens per session (2,113 once invoked), scanned A, original, MIT.

A guide to testing and improving AI agents, language models, prompts, code, and workflows. It covers evaluation files, simulated test data, trace review, and repeatable improvement loops.

In plain words
What is it for?
Use it to create evaluations, define judges and grading rules, generate simulation data, inspect traces, compare results, and run focused improvement cycles.
Why use it?
It helps teams base changes on test failures, observed behavior, benchmark results, or human feedback instead of guesswork.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agent-skills plugin — 57 skills shipped together

Good fit Use it to create evaluations, define judges and grading rules, generate simulation data, inspect traces, compare results, and run focused improvement cycles.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tyler-r-kendrick/agent-skills/improve
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Tyler-R-Kendrick/agent-skills --skill improve
Clone the repo
git clone --depth 1 https://github.com/Tyler-R-Kendrick/agent-skills

Made for: Claude Code.

Or install agent-skills, the plugin that ships this one along with the rest of its 57 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for improve

README.md
[![agentmods](https://agentmods.dev/badge/skills/tyler-r-kendrick/agent-skills/improve/github.svg)](https://agentmods.dev/skills/tyler-r-kendrick/agent-skills/improve)
Your own site
<a href="https://agentmods.dev/skills/tyler-r-kendrick/agent-skills/improve"><img src="https://agentmods.dev/badge/skills/tyler-r-kendrick/agent-skills/improve/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for improve

Your own site · 80×15
<a href="https://agentmods.dev/skills/tyler-r-kendrick/agent-skills/improve"><img src="https://agentmods.dev/badge/skills/tyler-r-kendrick/agent-skills/improve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 215 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,113 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00215 $0.02113
Opus 5 $0.00108 $0.01056
Sonnet 5 $0.00043 $0.00423
Haiku 4.5 $0.00021 $0.00211

Measured 12d ago against content hash 1112baffb20e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

improve scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/improve-cli.test.ts, scripts/improve-cli.ts, scripts/simulation-lib.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/ai/improve/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evals and Self-Improvement Pipelines

Operating Rule

Default new agent and LLM evals to AgentEvals EVAL.yaml with AgentV. Improve only against evidence: eval failures, trace observations, benchmark deltas, human review notes, or explicit user goals. Keep each loop narrow, reproducible, and auditable.

Progressive Disclosure

Load only the reference needed for the requested eval or improvement surface:

If the task says... Then read...
"install", "setup", "environment", "venv", "dependencies", "API keys", "Node", "Python", or missing native tools references/environment-setup.md
"install AgentV", "install ASSERT", "setup eval tools", "eval runner install", or native eval validation setup references/install-eval-tools.md
"install GEPA", "install Trace", "install Agent Lightning", "install SkillOpt", "setup optimizer", or improvement library dependencies references/install-improvement-libs.md
"create an eval", "judge", "grader", "rubric", "EVAL.yaml", or no eval standard references/agentevals.md and references/agentv.md
"which eval standard", "convert eval", "compare standards", or mixed eval formats references/eval-standards-guide.md
"Agent Skills eval", evals.json, "skill quality", "with_skill", or "without_skill" references/agent-skills-evals.md
"ASSERT", assert-ai, "judge-traces", "spec-driven", "behavior taxonomy", "trace-aware", "policy failure modes", or eval_config.yaml references/assert.md
"eval starter", "eval lint", "eval workspace contract", or expected eval artifacts references/eval-workspace-contracts.md
"optimize a skill", "progressive disclosure", "Table of Contents", "Index Page", "conditional access", "top-level links", "scripted workflow", or "deterministic workflow generation" references/skill-optimization-strategy.md
"which technique", "optimize this", "improvement plan", or mixed artifacts references/techniques-guide.md
"GEPA", "Pareto", "reflective mutation", "prompt evolution", or "optimize anything" references/gepa.md
"Trace", "OptoPrime", "computation graph", "node", "bundle", or end-to-end generative optimization references/microsoft-trace.md
"VISTA", "interpretable APO", "hypothesis agent", "random restart", or "epsilon-greedy" references/vista.md
"Agent Lightning", "RL", "reward", "policy reward", "governed training", or skill improvement with policy constraints references/agent-lightning.md
"SkillOpt", "SkillOpts", "skill evolution", best_skill.md, "held-out gate", "bounded edits", "textual learning rate", or "SkillOpt-Sleep" references/skillopt.md
"eval failures", "agent traces", "span logs", "benchmark deltas", or "release evidence" references/eval-trace-improvement.md
"synthetic data", "simulation data", "Simula", "QDC", "Source2Synth", "MAG-V", "MetaSynth", "BARE", "Condor", "data auditor", "generate data", or "simulate" references/simulation-data.md
"CLI", "init", "improve", "eval", "simulate", "lint", "workspace", or "deterministic improvement artifacts" references/workspace-contracts.md

Read the full file on GitHub · 106 lines

Files

What ships with it

44 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 106 lines · 215 tokens per session scan A 1112baffb20e

Subscribe to this mod's changes

improve is a skill published in the GitHub repository Tyler-R-Kendrick/agent-skills (11 stars, last pushed 3mo ago), licensed MIT. It adds 215 tokens to every session and 2,113 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens